Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    file paths and URLs in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    File paths or code snippets containing "/" character

    np_acts-logits-general · gemini-2.0-flash

    file paths and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſind
    -0.65
    Datuak
    -0.62
     queſta
    -0.61
    MemoryWarning
    -0.60
    躇
    -0.57
    MockBean
    -0.55
    esgue
    -0.55
     plufieurs
    -0.55
     dezelve
    -0.54
    btnut
    -0.54
    POSITIVE LOGITS
    /
    1.87
     /
    1.40
    ()/
    1.23
    -/
    1.18
    }/
    1.17
    |/
    1.16
    {}/
    1.16
    '/
    1.14
    ]/
    1.13
    ／
    1.12
    Act Density 0.396%

    No Known Activations